{"id":"W2907670343","doi":"10.48550/arxiv.1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Hyperparameter optimization; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Mathematical optimization; Mathematics; Support vector machine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002839566,0.002191035,0.00158706,0.0009016031,0.0005165098,0.001734492,0.002042945,0.002925786,0.003377014],"category_scores_gemma":[0.01272897,0.001281287,0.000975945,0.0009485323,0.001964808,0.00270228,0.002197533,0.003406494,0.001307068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001322199,"about_ca_system_score_gemma":0.001606422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00308902,"about_ca_topic_score_gemma":0.003661109,"domain_scores_codex":[0.9988668,0.0005662843,0.00005225953,0.0002407917,0.0001754905,0.00009837183],"domain_scores_gemma":[0.9973679,0.001765569,0.0002395686,0.0002587024,0.0002752203,0.00009299948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004045995,0.00003435317,0.0003273352,0.0000487847,0.00003650764,0.00003062684,0.00005266293,0.9685089,0.000910087,0.008383799,0.001113977,0.02051254],"study_design_scores_gemma":[0.00000713779,0.00001023812,0.00002574227,0.00001240882,0.000003563857,0.000007250865,0.000005329796,0.991309,0.0003030716,0.008075207,0.0002362398,0.000004756803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008954723,0.000233289,0.9884799,0.000195649,0.00002249327,0.0000473207,0.00004104105,0.000544867,0.001480768],"genre_scores_gemma":[0.5529955,0.0004812138,0.4390579,0.0006685629,0.00008676977,0.0007094236,0.0003497049,0.0009282802,0.004722831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003377014,"threshold_uncertainty_score":0.01501721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04801974787008525,"score_gpt":0.1928887671788964,"score_spread":0.1448690193088112,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}